SUTD Visual Computing Group

awesome-generative-modeling-under-data-constraints

A Comprehensive List of Works for Generative Modeling with Limited Data, Few Shots, and Zero Shot

dag-gans

Data Augmentation optimized for GAN

Fourier-Discrepancies-CNN-Detection

[CVPR 2021: Oral] In this work, we show that high frequency Fourier spectrum decay discrepancies are not inherent characteristics for existing CNN-based generative models.

google-streetview-gis-stack

This tool helps to generate Google Street View coverage maps by leveraging on Geographic Information System and Google Static Street View API

KML-Classification

[NeurIPS 2021] Revisit Multimodal Meta-Learning through the Lens of Multi-Task Learning | PyTorch Implementation

label-smoothing-multi-label-classification

Label Smoothing Experiment for Multi-label classification using Pascal VOC 2012 dataset

LS-KD-compatibility

[ICML 2022] This work investigates the compatibility between label smoothing (LS) and knowledge distillation (KD). We suggest to use an LS-trained teacher with a low-temperature transfer to render high performance students.

Re-thinking_MI

[CVPR-2023] Re-thinking Model Inversion Attacks Against Deep Neural Networks

tokyo_24-7_image_retrieval_annotations

Annotated subset of Tokyo 24/7 Google Street View Dataset for Visual Geo-localization research. It consists of 16,000 dataset images and 49 distinct query locations taken at day/ evening/ night for a total of 147 query images.

transferable-forensic-features

[ECCV 2022: Oral] In this work, we discover that color is a crtical transferable forensic feature (T-FF) in universal detectors for detecting CNN-generated images.

sutd-visual-computing-group/dag-gans

Data Augmentation optimized for GAN

sutd-visual-computing-group/Re-thinking_MI

[CVPR-2023] Re-thinking Model Inversion Attacks Against Deep Neural Networks

sutd-visual-computing-group/Fourier-Discrepancies-CNN-Detection

[CVPR 2021: Oral] In this work, we show that high frequency Fourier spectrum decay discrepancies are not inherent characteristics for existing CNN-based generative models.

sutd-visual-computing-group/awesome-generative-modeling-under-data-constraints

A Comprehensive List of Works for Generative Modeling with Limited Data, Few Shots, and Zero Shot

sutd-visual-computing-group/transferable-forensic-features

[ECCV 2022: Oral] In this work, we discover that color is a crtical transferable forensic feature (T-FF) in universal detectors for detecting CNN-generated images.

sutd-visual-computing-group/LS-KD-compatibility

[ICML 2022] This work investigates the compatibility between label smoothing (LS) and knowledge distillation (KD). We suggest to use an LS-trained teacher with a low-temperature transfer to render high performance students.

sutd-visual-computing-group/KML-Classification

[NeurIPS 2021] Revisit Multimodal Meta-Learning through the Lens of Multi-Task Learning | PyTorch Implementation

sutd-visual-computing-group/tokyo_24-7_image_retrieval_annotations

Annotated subset of Tokyo 24/7 Google Street View Dataset for Visual Geo-localization research. It consists of 16,000 dataset images and 49 distinct query locations taken at day/ evening/ night for a total of 147 query images.

sutd-visual-computing-group/google-streetview-gis-stack

This tool helps to generate Google Street View coverage maps by leveraging on Geographic Information System and Google Static Street View API

sutd-visual-computing-group/label-smoothing-multi-label-classification

Label Smoothing Experiment for Multi-label classification using Pascal VOC 2012 dataset

sutd-visual-computing-group/research-reproducibility-guide-book

This Guide book is written with the intention of helping researchers and engineers working in machine learning domains to publish reproducible research.

sutd-visual-computing-group/FairTL

sutd-visual-computing-group/multimodal-fisher-vector

[ICASSP 2016] Dataset for egocentric activity recognition : "Egocentric Activity Recognition with Multimodal Fisher Vector"

sutd-visual-computing-group/sutd-visual-computing-group.github.io

sutd-visual-computing-group/AdAM

sutd-visual-computing-group/CLEAM